Black Forest Labs

FLUX.2 Klein 9BTerbuka

9B FLUX.2 klein tier — near-Pro quality on a single consumer GPU.

#28dirilis 14 Okt 2026·Open Weights·9B
textimage64K ctx
Penyedia APIJalankan Model →Peringkat
Inteligensi
88.2 #28
AAQI 88.0
Kecepatan output
55 t/s
ITL 18.2 ms/tok
Harga gabungan (3:1)
$0.02 /1M
Input $0.02/M · Output $0.02/M
Konteks
64K
≈ 160 halaman A4 · output maks 4,096

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

FLUX.2 Klein 9B
Claude Mythos Preview (#1)
Average (68)
Coding (15)Mathematics (15)Hard Science (GPQA) (32)Agentic & Tool Use (22)Knowledge (MMLU) (50)Vision / Multimodal (94)

Sumbu radar diaproksimasi dari skor kategori jika pengukuran benchmark langsung tidak tersedia — lihat Metodologi.

Kelebihan & Trade-off

Di mana ia menang

  • Best quality-per-GB in the FLUX.2 family
  • Runs on RTX 3060-class hardware
  • Open weights — fine-tune and self-host freely

Hal yang perlu diperhatikan

  • Still trails Dev/Pro on typography and faces
  • Half the speed of the 4B klein tier
  • 2K output ceiling

Kasus Penggunaan Killer

Hobbyist & indie pipelines
Pro-adjacent images on consumer cards.
Fine-tuned niche styles
Small enough to iterate LoRAs overnight.
Local production tools
Self-hosted rendering for studios and agencies.

Quickstart Developer & API

Atur HF_TOKEN dulu — dapatkan kunci API
curl https://router.huggingface.co/v1/chat/completions \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "content-type: application/json" \
  -d '{
    "model": "black-forest-labs/FLUX.2-klein-9b",
    "messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
  }'

Sumber Daya & Tautan Resmi

Deployment API

Bandingkan host & latensi

Throughput, TTFT, dan harga cache di Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock, dan Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Lihat matriks penyedia →

Skor per sumber

Spesifikasi Live & Arsitektur

Di balik kap
FLUX.2 Klein 9B — consumer-GPU diffusion
  • 9B distilled transformer — the klein quality tier
  • Fits 8GB VRAM at Q4
  • Near-Pro prompt adherence on standard scenes
  • Full LoRA fine-tuning support
Tanggal rilis
14 Okt 2026
Arsitektur
FLUX.2 Klein 9B — consumer-GPU diffusion
Parameter
9B
Lisensi
Open Weights
Jendela konteks
64,000 tokens
Output maks
4,096 tokens
Modalitas
text + image
Harga cache
baca $0.008 · tulis $0.025 /1M
Penalaran
—
Harga input
$0.02/M
Harga output
$0.02/M
Kecepatan output
55 t/s
Waktu ke token pertama
—
Data diperbarui
22 Okt 2026
Perangkat Keras & Inferensi Lokal
Data: Convly AI (CC BY 4.0) ↗
VRAM (4-bit Q4)
6 GB
GPU Min.
RTX 3060 8GB / any 8GB GPU

Estimasi tagihan bulanan

Estimasi pengeluaran bulanan
$0.00
Menghitung penghematan vs GPT-4o…

Kutip & sematkan

Badge Markdown GitHub
Loading badge markdown...
BibTeX
@misc{llmpodium2026flux2klein9b,
  title = {Benchmark Analysis and Intelligence Evaluation of FLUX.2 Klein 9B},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/flux-2-klein-9b}
}

Sematkan Lencana Skor

Tambahkan lencana Podium Score langsung ke README GitHub atau Hugging Face Anda — menautkan ke peringkat langsung.

Pratinjau
FLUX.2 Klein 9B LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Lainnya dari Black Forest Labs

Model Alternatif

Alternatif terdekat untuk FLUX.2 Klein 9B berdasarkan kemampuan, harga, dan skor benchmark.

0 / 4